(转) GAN论文整理
本文转自:http://www.jianshu.com/p/2acb804dd811
GAN论文整理
原始GAN
Goodfellow和Bengio等人发表在NIPS 2014年的文章Generative adversary network,是生成对抗网络的开创文章,论文思想启发自博弈论中的二人零和博弈。在二人零和博弈中,两位博弈方的利益之和为零或一个常数,即一方有所得,另一方必有所失。GAN模型中的两位博弈方分别由生成式模型(generative model)和判别式模型(discriminative model)充当。生成模型G捕捉样本数据的分布,判别模型D是一个二分类器,估计一个样本来自于训练数据(而非生成数据)的概率。G和D一般都是非线性映射函数,例如多层感知机、卷积神经网络等。
如图所示,左图是一个判别式模型,当输入训练数据x时,期待输出高概率(接近1);右图下半部分是生成模型,输入是一些服从某一简单分布(例如高斯分布)的随机噪声z,输出是与训练图像相同尺寸的生成图像。向判别模型D输入生成样本,对于D来说期望输出低概率(判断为生成样本),对于生成模型G来说要尽量欺骗D,使判别模型输出高概率(误判为真实样本),从而形成竞争与对抗。
GAN优势很多:根据实际的结果,看上去产生了更好的样本;GAN能训练任何一种生成器网络;GAN不需要设计遵循任何种类的因式分解的模型,任何生成器网络和任何鉴别器都会有用;GAN无需利用马尔科夫链反复采样,无需在学习过程中进行推断,回避了近似计算棘手的概率的难题。
GAN主要存在的以下问题:网络难以收敛,目前所有的理论都认为GAN应该在纳什均衡上有很好的表现,但梯度下降只有在凸函数的情况下才能保证实现纳什均衡。
GAN发展
一方面GAN的发展很快,这里只是简单粗略将相关论文分了几类,欢迎反馈,持续更新。此外最近ICLR 2017 在进行Open Review,可以关注下ICLR 2017 Conference Track,也有相应论文笔记分享ICLR 2017 | GAN Missing Modes 和 GAN
GAN从2014年到现在发展很快,特别是最近ICLR 2016/2017关于GAN的论文很多,GAN现在有很多问题还有到解决,潜力很大。总体可以将已有的GANs论文分为以下几类
- GAN Theory
- GAN in Semi-supervised
- Muti-GAN
- GAN with other Generative model
- GAN with RNN
- GAN in Application
GAN Theory
此类关注与无监督GAN本身原理的研究:比较两个分布的距离;用DL的一些方法让GAN快速收敛等等。相关论文有:
- GAN: Goodfellow, Ian, et al. "Generative adversarial nets." Advances in Neural Information Processing Systems. 2014.
- LAPGAN: Denton, Emily L., Soumith Chintala, and Rob Fergus. "Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks." Advances in neural information processing systems. 2015.
- DCGAN: Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv preprint arXiv:1511.06434 (2015).
- Improved GAN: Salimans, Tim, et al. "Improved techniques for training gans." arXiv preprint arXiv:1606.03498 (2016).
- InfoGAN: Chen, Xi, et al. "Infogan: Interpretable representation learning by information maximizing generative adversarial nets." arXiv preprint arXiv:1606.03657(2016).**
- EnergyGAN: Zhao, Junbo, Michael Mathieu, and Yann LeCun. "Energy-based Generative Adversarial Network." arXiv preprint arXiv:1609.03126 (2016).
- Creswell, Antonia, and Anil A. Bharath. "Task Specific Adversarial Cost Function." arXiv preprint arXiv:1609.08661 (2016).
- f-GAN: Nowozin, Sebastian, Botond Cseke, and Ryota Tomioka. "f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization." arXiv preprint arXiv:1606.00709 (2016).
- Unrolled Generative Adversarial Networks, ICLR 2017 Open Review
- Improving Generative Adversarial Networks with Denoising Feature Matching, ICLR 2017 Open Review
- Mode Regularized Generative Adversarial Networks, ICLR 2017 Open Review
- b-GAN: Unified Framework of Generative Adversarial Networks, ICLR 2017 Open Review
- Mohamed, Shakir, and Balaji Lakshminarayanan. "Learning in Implicit Generative Models." arXiv preprint arXiv:1610.03483 (2016).
GAN in Semi-supervised
此类研究将GAN用于半监督学习,相关论文有:
- Springenberg, Jost Tobias. "Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks." arXiv preprint arXiv:1511.06390 (2015).
- Odena, Augustus. "Semi-Supervised Learning with Generative Adversarial Networks." arXiv preprint arXiv:1606.01583 (2016).
Muti-GAN
此类研究将多个GAN进行组合,相关论文有:
- CoupledGAN: Liu, Ming-Yu, and Oncel Tuzel. "Coupled Generative Adversarial Networks." arXiv preprint arXiv:1606.07536 (2016).
- Wang, Xiaolong, and Abhinav Gupta. "Generative Image Modeling using Style and Structure Adversarial Networks." arXiv preprint arXiv:1603.05631(2016).
- Generative Adversarial Parallelization, ICLR 2017 Open Review
- LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation, ICLR 2017 Open Review
GAN with other Generative model
此类研究将GAN与其他生成模型组合,相关论文有:
- Dosovitskiy, Alexey, and Thomas Brox. "Generating images with perceptual similarity metrics based on deep networks." arXiv preprint arXiv:1602.02644(2016).
- Larsen, Anders Boesen Lindbo, Søren Kaae Sønderby, and Ole Winther. "Autoencoding beyond pixels using a learned similarity metric." arXiv preprint arXiv:1512.09300 (2015).
- Theis, Lucas, and Matthias Bethge. "Generative image modeling using spatial lstms." Advances in Neural Information Processing Systems. 2015.
GAN with RNN
此类研究将GAN与RNN结合(也以参考Pixel RNN),相关论文有:
- Im, Daniel Jiwoong, et al. "Generating images with recurrent adversarial networks." arXiv preprint arXiv:1602.05110 (2016).
- Kwak, Hanock, and Byoung-Tak Zhang. "Generating Images Part by Part with Composite Generative Adversarial Networks." arXiv preprint arXiv:1607.05387 (2016).
- Yu, Lantao, et al. "SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient." arXiv preprint arXiv:1609.05473 (2016).
GAN in Application
此类研究将GAN的实际运用(不包括图像生成),相关论文有:
- Zhu, Jun-Yan, et al. "Generative visual manipulation on the natural image manifold." European Conference on Computer Vision. Springer International Publishing, 2016.
- Creswell, Antonia, and Anil Anthony Bharath. "Adversarial Training For Sketch Retrieval." European Conference on Computer Vision. Springer International Publishing, 2016.
- Reed, Scott, et al. "Generative adversarial text to image synthesis." arXiv preprint arXiv:1605.05396 (2016).
- Ravanbakhsh, Siamak, et al. "Enabling Dark Energy Science with Deep Generative Models of Galaxy Images." arXiv preprint arXiv:1609.05796(2016).
- Abadi, Martín, and David G. Andersen. "Learning to Protect Communications with Adversarial Neural Cryptography." arXiv preprint arXiv:1610.06918(2016).
- Odena, Augustus, Christopher Olah, and Jonathon Shlens. "Conditional Image Synthesis With Auxiliary Classifier GANs." arXiv preprint arXiv:1610.09585 (2016).
- Ledig, Christian, et al. "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network." arXiv preprint arXiv:1609.04802 (2016).
- Nguyen, Anh, et al. "Synthesizing the preferred inputs for neurons in neural networks via deep generator networks." arXiv preprint arXiv:1605.09304(2016).
(转) GAN论文整理的更多相关文章
- REST架构简析(原论文整理)
0 引言 目前,互联网在社会中扮演的角色越来越重要.通过互联网为广大群众提供服务,也是互联网成功的关键.互联网服务架构目前大多数都是基于REST架构来完成的.REST从它诞生至今,可以说 ...
- Generative Adversarial Networks,gan论文的畅想
前天看完Generative Adversarial Networks的论文,不知道有什么用处,总想着机器生成的数据会有机器的局限性,所以百度看了一些别人 的看法和观点,可能我是机器学习小白吧,看完之 ...
- 深度学习-Wasserstein GAN论文理解笔记
GAN存在问题 训练困难,G和D多次尝试没有稳定性,Loss无法知道能否优化,生成样本单一,改进方案靠暴力尝试 WGAN GAN的Loss函数选择不合适,使模型容易面临梯度消失,梯度不稳定,优化目标不 ...
- CVPapers论文整理工具-开源
一.工具介绍及运行实例 相信计算机视觉领域的同道中人都知道这个Computer Vision Resource网站, http://www.cvpapers.com/ 网页部分截图如下: 可以看到有 ...
- 条件GAN论文简单解读
条件GAN(Conditional Generative Adversarial Nets),原文地址为CGAN. Abstract 生成对抗网络(GAN)是最近提出的训练生成模型(g ...
- OCR论文整理
论文地址:https://github.com/ChanChiChoi/awesome-ocr 下面是已经看过的论文: CTPN CRNN TextBoxes EAST FOTS PixelLink
- Gan-based zero-shot learning 论文整理
1 Feature Generating Networks for Zero-Shot Learning Suffering from the extreme training data imbala ...
- 《Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering》论文整理
融合异构知识进行常识问答 论文标题 -- <Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense ...
- 网络压缩论文整理(network compression)
1. Parameter pruning and sharing 1.1 Quantization and Binarization Compressing deep convolutional ne ...
随机推荐
- Widget Factory (高斯消元解线性方程组)
The widget factory produces several different kinds of widgets. Each widget is carefully built by a ...
- 20165305 学习基础和C语言基础调查
学习基础和C语言基础调查 <优秀的教学方法---做教练与做中学>心得 在<优秀的教学方法---做教练与做中学>文章中又一次提到了"做教练"这一学习方法,因为 ...
- linux常用命令:touch 命令
linux的touch命令不常用,一般在使用make的时候可能会用到,用来修改文件时间戳,或者新建一个不存在的文件. 1.命令格式: touch [选项]... 文件... 2.命令参数: -a ...
- IDEA相关知识整理
一.离线下载插件[也可以通过代理的方式下载插件] http://plugins.jetbrains.com/ 下载离线插件 settings -> plugins -> install p ...
- Android获取全局Context的方法
Android获取全局Context的方法 Android--应用全局获取Context - 超宇的博客 - CSDN博客https://blog.csdn.net/chaoyu168/article ...
- android studio 自动导入包
android studio 自动导入包 一.Android studio 的导单个包的快捷键是Alt+Enter (需要选中要导入包的类名再按快捷键才起作用): 二.Android studio 可 ...
- highchart 柱状图 分组样例
var chart = Highcharts.chart('container',{ chart: { type: 'column' }, title: { text: '月平均降雨量' }, sub ...
- nginx FastCGI错误Primary script unknown解决办法
在centos上成功编译安装nginx 1.4.php 5.4并成功启动nginx和php-fpm后,访问php提示"File not found.",同时在错误日志中看到: 复制 ...
- MVC 部署HTTPS网站
一.项目配置 什么是全站HTTPS 全站HTTPS就是指整个网站的所有页面,所有资源全部使用HTTPS链接.当用户的某个请求是明文的HTTP时,应该通过HTTP状态码301永久重定向到对应的HTTPS ...
- node.js的on、emit、off封装
//绑定事件.触发事件和移除事件 //绑定事件 //on(eventName,cb){} //第一步判断当前事件是否存在,如果不存在则初始化:key:[],然后在将回调函数添加到数据中去 let ev ...